Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e97bd296e883539018dac2ffe46aed430c2ce0fe546710541cfb36d7621cee
+oid sha256:983826318c7057d7d63874912a6010d0070cd5323a56cd326399e36401483527
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06904eaa66bcdf5fb5698e14b602a4fa7ed63d748a149fa8ce1b94bef7b4096e
+oid sha256:ae136e4335a2973ca460d3af852eeac6c7a1da061fd720a2f9c6be2ace6ee34b
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cad2658200f2482b7574bdc57c18294b67c90589354a1df1f50b18ca492e76c
+oid sha256:23b292c0efb28eea88c002c7c382d68ce9c4cd641c1f3fb777ab6b43a2d8a19d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02796420581655481,
+  "epoch": 0.037285607755406416,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.4399,
       "step": 75
+    },
+    {
+      "epoch": 0.028337061894108874,
+      "grad_norm": 1.640629768371582,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4401,
+      "step": 76
+    },
+    {
+      "epoch": 0.02870991797166294,
+      "grad_norm": 2.2154061794281006,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.4543,
+      "step": 77
+    },
+    {
+      "epoch": 0.029082774049217,
+      "grad_norm": 2.167428970336914,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4523,
+      "step": 78
+    },
+    {
+      "epoch": 0.029455630126771066,
+      "grad_norm": 1.528300166130066,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3186,
+      "step": 79
+    },
+    {
+      "epoch": 0.02982848620432513,
+      "grad_norm": 2.0265486240386963,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3924,
+      "step": 80
+    },
+    {
+      "epoch": 0.030201342281879196,
+      "grad_norm": 2.0504417419433594,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.6672,
+      "step": 81
+    },
+    {
+      "epoch": 0.030201342281879196,
+      "eval_loss": 0.23957125842571259,
+      "eval_runtime": 352.949,
+      "eval_samples_per_second": 6.4,
+      "eval_steps_per_second": 0.802,
+      "step": 81
+    },
+    {
+      "epoch": 0.030574198359433258,
+      "grad_norm": 2.563886880874634,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7267,
+      "step": 82
+    },
+    {
+      "epoch": 0.030947054436987323,
+      "grad_norm": 1.796322226524353,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.3949,
+      "step": 83
+    },
+    {
+      "epoch": 0.03131991051454139,
+      "grad_norm": 1.647054672241211,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.417,
+      "step": 84
+    },
+    {
+      "epoch": 0.03169276659209545,
+      "grad_norm": 1.86093270778656,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5066,
+      "step": 85
+    },
+    {
+      "epoch": 0.03206562266964952,
+      "grad_norm": 1.2961095571517944,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3748,
+      "step": 86
+    },
+    {
+      "epoch": 0.03243847874720358,
+      "grad_norm": 2.5816919803619385,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.5375,
+      "step": 87
+    },
+    {
+      "epoch": 0.03281133482475764,
+      "grad_norm": 2.0271952152252197,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5459,
+      "step": 88
+    },
+    {
+      "epoch": 0.03318419090231171,
+      "grad_norm": 1.8496075868606567,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.5836,
+      "step": 89
+    },
+    {
+      "epoch": 0.03355704697986577,
+      "grad_norm": 1.6776535511016846,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2553,
+      "step": 90
+    },
+    {
+      "epoch": 0.03355704697986577,
+      "eval_loss": 0.23708520829677582,
+      "eval_runtime": 352.9201,
+      "eval_samples_per_second": 6.401,
+      "eval_steps_per_second": 0.802,
+      "step": 90
+    },
+    {
+      "epoch": 0.03392990305741984,
+      "grad_norm": 2.3019521236419678,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.418,
+      "step": 91
+    },
+    {
+      "epoch": 0.0343027591349739,
+      "grad_norm": 1.7794111967086792,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.4092,
+      "step": 92
+    },
+    {
+      "epoch": 0.03467561521252797,
+      "grad_norm": 1.2687029838562012,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3775,
+      "step": 93
+    },
+    {
+      "epoch": 0.035048471290082026,
+      "grad_norm": 3.371903657913208,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6589,
+      "step": 94
+    },
+    {
+      "epoch": 0.03542132736763609,
+      "grad_norm": 4.147241592407227,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3095,
+      "step": 95
+    },
+    {
+      "epoch": 0.035794183445190156,
+      "grad_norm": 1.5110682249069214,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.3949,
+      "step": 96
+    },
+    {
+      "epoch": 0.03616703952274422,
+      "grad_norm": 1.5129752159118652,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.387,
+      "step": 97
+    },
+    {
+      "epoch": 0.036539895600298286,
+      "grad_norm": 2.31642484664917,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7087,
+      "step": 98
+    },
+    {
+      "epoch": 0.03691275167785235,
+      "grad_norm": 3.623220443725586,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5247,
+      "step": 99
+    },
+    {
+      "epoch": 0.03691275167785235,
+      "eval_loss": 0.23658187687397003,
+      "eval_runtime": 352.981,
+      "eval_samples_per_second": 6.4,
+      "eval_steps_per_second": 0.802,
+      "step": 99
+    },
+    {
+      "epoch": 0.037285607755406416,
+      "grad_norm": 1.4099475145339966,
+      "learning_rate": 0.0,
+      "loss": 0.3286,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.521684545536e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null